This repository presents the source code for the paper "MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization" (DAC'25).
☆25Apr 2, 2025Updated last year
Alternatives and similar repositories for MILLION
Users that are interested in MILLION are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ☆19Nov 11, 2024Updated last year
- TransPimLib is a library for transcendental (and other hard-to-calculate) functions in general-purpose PIM systems, TransPimLib provides …☆16Apr 21, 2023Updated 3 years ago
- Implementation of NM sparsity recipe presented in the paper "Progressive Gradient Flow for Robust N:M Sparsity Training in Transformers".☆11Feb 5, 2024Updated 2 years ago
- Efficient Expert Pruning for Sparse Mixture-of-Experts Language Models: Enhancing Performance and Reducing Inference Costs☆25Nov 11, 2025Updated 8 months ago
- LoAS: Fully Temporal-Parallel Dataflow for Dual-Sparse Spiking Neural Networks, MICRO 2024.☆19Mar 19, 2025Updated last year
- Proton VPN Special Offer - Get 70% off • AdSpecial partner offer. Trusted by over 100 million users worldwide. Tested, Approved and Recommended by Experts.
- ☆12Aug 18, 2023Updated 2 years ago
- ☆19Jul 3, 2026Updated 2 weeks ago
- High Performance Int8 GEMM Kernels for SM80 and later GPUs.☆23Mar 11, 2025Updated last year
- PIM-DL: Expanding the Applicability of Commodity DRAM-PIMs for Deep Learning via Algorithm-System Co-Optimization☆37Feb 21, 2024Updated 2 years ago
- ☆42Mar 28, 2024Updated 2 years ago
- [ICML 2025] CommVQ: Commutative Vector Quantization for KV Cache Compression☆27Sep 2, 2025Updated 10 months ago
- [ICLR'25] R-Sparse: Rank-Aware Activation Sparsity for Efficient LLM Inference☆21Apr 28, 2025Updated last year
- Open source RTL implementation of Tensor Core, Sparse Tensor Core, BitWave and SparSynergy in the article: "SparSynergy: Unlocking Flexib…☆26Mar 29, 2025Updated last year
- ☆11Jun 11, 2023Updated 3 years ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- ☆10Jun 10, 2023Updated 3 years ago
- Large Language Model Inference Acceleration: A Comprehensive Hardware Perspective☆18Jul 15, 2025Updated last year
- A simple script to plot the Roofline model for given HW platforms and applications☆10Mar 17, 2026Updated 4 months ago
- Thysrael's naive dotfiles.☆17Updated this week
- GPGPU-Sim 中文注释版代码，包含 GPGPU-Sim 模拟器的最新版代码，经过中文注释，以帮助中文用户更好地理解和使用该模拟器。☆30Dec 18, 2024Updated last year
- Tender: Accelerating Large Language Models via Tensor Decompostion and Runtime Requantization (ISCA'24)☆34Jul 4, 2024Updated 2 years ago
- Influence-maximization-on-hypergraphs☆14Jun 6, 2022Updated 4 years ago
- Residual vector quantization for KV cache compression in large language model☆12Oct 22, 2024Updated last year
- Explore Inter-layer Expert Affinity in MoE Model Inference☆16May 6, 2024Updated 2 years ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- AFP is a hardware-friendly quantization framework for DNNs, which is contributed by Fangxin Liu and Wenbo Zhao.☆13Nov 8, 2021Updated 4 years ago
- ☆123Nov 17, 2023Updated 2 years ago
- Light weight threading library for gem5 syscall emulator (git mirror)☆16Mar 1, 2017Updated 9 years ago
- ☆23Apr 3, 2026Updated 3 months ago
- [OSDI 2025] DecDEC: A Systems Approach to Advancing Low‑Bit LLM Quantization☆26Jan 29, 2026Updated 5 months ago
- Offical implementation of "MetaLA: Unified Optimal Linear Approximation to Softmax Attention Map" (NeurIPS2024 Oral)☆36Jan 18, 2025Updated last year
- ☆21Apr 3, 2025Updated last year
- [ACL 2024 Findings] Light-PEFT: Lightening Parameter-Efficient Fine-Tuning via Early Pruning☆13Sep 2, 2024Updated last year
- ☆18Nov 10, 2025Updated 8 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆68Nov 29, 2025Updated 7 months ago
- Agent application/benchmark/workload traces should be placed here.☆15Apr 13, 2026Updated 3 months ago
- Compressible Dynamics in Deep Overparameterized Low-Rank Learning & Adaptation (ICML'24 Oral)☆12Jul 22, 2024Updated last year
- The official implementation of HPCA 2025 paper, Prosperity: Accelerating Spiking Neural Networks via Product Sparsity☆41Aug 9, 2025Updated 11 months ago
- GOMIL: Global Optimization of Multiplier by Integer Linear Programming☆13Aug 25, 2021Updated 4 years ago
- ASIC simulation of Multi-ported Memory Module. And it can offer SRAM-based dual-port basic building block to support multiple read/write …☆25May 30, 2016Updated 10 years ago
- Official Pytorch Implementation of Paper "DarwinLM: Evolutionary Structured Pruning of Large Language Models"☆20Feb 21, 2025Updated last year